形状必须是等阶的，但是是 2 和 1

Question

我在 youtube 上关注 Sentdex 的示例，这是我拥有的代码

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("/tmp/data/", one_hot = True)

n_nodes_hl1 = 500
n_nodes_hl2 = 500
n_nodes_hl3 = 500

n_classes = 10
batch_size = 100

x = tf.placeholder('float', [None, 784])
y = tf.placeholder('float')

def neural_network_model(data):
    hidden_1_layer = {'weights':tf.Variable(tf.random_normal([784, n_nodes_hl1])),
                      'biases':tf.Variable(tf.random_normal([n_nodes_hl1]))}

    hidden_2_layer = {'weights':tf.Variable(tf.random_normal([n_nodes_hl1, n_nodes_hl2])),
                      'biases':tf.Variable(tf.random_normal([n_nodes_hl2]))}

    hidden_3_layer = {'weights':tf.Variable(tf.random_normal([n_nodes_hl2, n_nodes_hl3])),
                      'biases':tf.Variable(tf.random_normal([n_nodes_hl3]))}

    output_layer = {'weights':tf.Variable(tf.random_normal([n_nodes_hl3, n_classes])),
                    'biases':tf.Variable(tf.random_normal([n_classes])),}


    l1 = tf.add(tf.matmul(data,hidden_1_layer['weights']), hidden_1_layer['biases'])
    l1 = tf.nn.relu(l1)

    l2 = tf.add(tf.matmul(l1,hidden_2_layer['weights']), hidden_2_layer['biases'])
    l2 = tf.nn.relu(l2)

    l3 = tf.add(tf.matmul(l2,hidden_3_layer['weights']), hidden_3_layer['biases'])
    l3 = tf.nn.relu(l3)

    output = tf.matmul(l3,output_layer['weights']) + output_layer['biases']

    return output

def train_neural_network(x):
    prediction = neural_network_model(x)
    # OLD VERSION:
    #cost = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(prediction,y) )
    # NEW:
    cost = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(logits=prediction, labels=y) )
    optimizer = tf.train.AdamOptimizer().minimize(cost)

    hm_epochs = 10
    with tf.Session() as sess:
        # OLD:
        #sess.run(tf.initialize_all_variables())
        # NEW:
        sess.run(tf.global_variables_initializer())

        for epoch in range(hm_epochs):
            epoch_loss = 0
            for _ in range(int(mnist.train.num_examples/batch_size)):
                epoch_x, epoch_y = mnist.train.next_batch(batch_size)
                _, c = sess.run([optimizer, cost], feed_dict={x: epoch_x, y: epoch_y})
                epoch_loss += c

            print('Epoch', epoch, 'completed out of',hm_epochs,'loss:',epoch_loss)

        correct = tf.equal(tf.argmax(prediction, 1), tf.argmax(y, 1))

        accuracy = tf.reduce_mean(tf.cast(correct, 'float'))
        print('Accuracy:',accuracy.eval({x:mnist.test.images, y:mnist.test.labels}))

train_neural_network(x)

它引发了这个错误：

ValueError: Shapes must be equal rank, but are 2 and 1
From merging shape 0 with other shapes. for 'SparseSoftmaxCrossEntropyWithLogits/packed' (op: 'Pack') with input shapes: [?,10], [10].

在这一行：

cost = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(logits=prediction, labels=y) )

我认为是 y 的大小引起了错误，我尝试使用

cost = tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(
        prediction, tf.squeeze(y)))

我很确定这意味着成本函数会导致错误（如上所示）预测并且 y 的形状不同，但我对 TensorFlow 的了解不够深入，无法知道如何修复它。我什至不明白 y 的设置位置，我从教程中获得了大部分代码，并对其进行了修改以将其应用于不同的数据集。我该如何解决这个错误？

ps 我试图打印出预测，它给了我两个输出，我猜这就是错误的来源：

prediction
(<tf.Tensor 'MatMul_39:0' shape=(?, 10) dtype=float32>,
 <tf.Variable 'Variable_79:0' shape=(10,) dtype=float32_ref>)

Answer 1

由于您在读取输入数据时使用one_hot=True，因此只需为y 占位符定义正确的形状

# redefine the label and input with exact data type and shape
x = tf.placeholder(tf.float32, [None, 784])
y = tf.placeholder(tf.float32, shape=[None, n_classes])

Answer 2

在此语句中，右括号和字典括号之间有一个逗号：

 output_layer = {'weights':tf.Variable(tf.random_normal([n_nodes_hl3, n_classes])),'biases':tf.Variable(tf.random_normal([n_classes])),}

就在右括号之前：

...([n_classes])),}

Answer 3

#WORKING CODE
#I had the same problem as you, (not counting the comma) and i´m sorry i don´t remember the things i changed, but hopefully this will work


import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
mnist= input_data.read_data_sets("/tmp/data/", one_hot=True)
#10 clasees, 0-9
n_nodes_hl1=500
n_nodes_hl2=500
n_nodes_hl3=500

n_classes=10
batch_size=100
x=tf.placeholder('float',[None,784])
y=tf.placeholder('float')

def neural(data):
    hidden_1_layer={'weights':tf.Variable(tf.random_normal([784, n_nodes_hl1])),
    'biases':tf.Variable(tf.random_normal([n_nodes_hl1]))}
    hidden_2_layer={'weights':tf.Variable(tf.random_normal([n_nodes_hl1, n_nodes_hl2])),
    'biases':tf.Variable(tf.random_normal([n_nodes_hl2]))}
    hidden_3_layer={'weights':tf.Variable(tf.random_normal([n_nodes_hl2, n_nodes_hl3])),
    'biases':tf.Variable(tf.random_normal([n_nodes_hl3]))}
    output_layer={'weights':tf.Variable(tf.random_normal([n_nodes_hl3, n_classes])),
    'biases':tf.Variable(tf.random_normal([n_classes]))}

    l1=tf.add(tf.matmul(data, hidden_1_layer['weights']), hidden_1_layer['biases'])
    li= tf.nn.relu(l1)
    l2=tf.add(tf.matmul(l1, hidden_2_layer['weights']), hidden_2_layer['biases'])
    l2= tf.nn.relu(l2)
    l3=tf.add(tf.matmul(l2, hidden_3_layer['weights']), hidden_3_layer['biases'])
    l3= tf.nn.relu(l3)
    output= tf.matmul(l3, output_layer['weights'])+ output_layer['biases']
    return output
def train(x):
    prediction=neural(x)
    cost= tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=prediction,labels=y))
    optimizer=tf.train.AdamOptimizer().minimize(cost)
    hm_epochs=20

    with tf.Session() as sess:
        sess.run(tf.global_variables_initializer())

        for epoch in range(hm_epochs):
            epoch_loss=0
            for _ in range(int(mnist.train.num_examples/batch_size)):
                epoch_x,epoch_y = mnist.train.next_batch(batch_size)
                _,c=sess.run([optimizer,cost],feed_dict={x: epoch_x, y: epoch_y})
                epoch_loss += c
            print('Epoch', epoch, 'completed out of', hm_epochs, 'loss:',epoch_loss)

        correct= tf.equal(tf.argmax(prediction,1), tf.argmax(y,1))
        accuracy= tf.reduce_mean(tf.cast(correct,'float'))
        print('Accuracy:',accuracy.eval({x:mnist.test.images, y:mnist.test.labels}))

train(x)